Update app.py

app.py

@@ -1,28 +1,81 @@
 from dotenv import load_dotenv
-import streamlit as st
-import os
-import sqlite3
-import google.generativeai as genai
-from PIL import Image
 from PyPDF2 import PdfReader
 from langchain.text_splitter import RecursiveCharacterTextSplitter
 from langchain_google_genai import GoogleGenerativeAIEmbeddings, ChatGoogleGenerativeAI
 from langchain.vectorstores import FAISS
 from langchain.chains.question_answering import load_qa_chain
 from langchain.prompts import PromptTemplate
+import streamlit as st
+import os
+import sqlite3
+import google.generativeai as genai
+
+# Load environment variables
+load_dotenv()
 
-load_dotenv() # Load all env variables
+# Configure Genai Key
 genai.configure(api_key=os.getenv("GOOGLE_API_KEY"))
 
-# Function to load Google Gemini Model and provide responses
-def get_gemini_response(question, prompt=None, image=None):
-    model = genai.GenerativeModel("gemini-pro-vision" if image else "gemini-pro")
-    context = prompt[0] if prompt else None
-    inputs = [question, context, image] if prompt else [question, image]
-    response = model.generate_content(inputs)
-    return response.text
+# Initialize Streamlit app
+st.set_page_config(page_title="Q&A Demo")
+
+st.header("Gemini LLM Application")
+
+# Initialize session state for chat history if it doesn't exist
+if 'chat_history' not in st.session_state:
+    st.session_state['chat_history'] = []
+
+# Load Google Gemini Model
+model = genai.GenerativeModel("gemini-pro") 
+chat = model.start_chat(history=[])
 
-# Function to load PDF text
+# Function to get response from Gemini model
+def get_gemini_response(question):
+    response = chat.send_message(question)
+    return response
+
+# Function to read SQL query from database
+def read_sql_query(sql, db):
+    conn = sqlite3.connect(db)
+    cur = conn.cursor()
+    cur.execute(sql)
+    rows = cur.fetchall()
+    conn.commit()
+    conn.close()
+    return rows
+
+# Define prompt for Gemini model
+prompt = """
+You are an expert in converting English questions to SQL query!
+The SQL database has the name STUDENT and has the following columns - NAME, CLASS, SECTION \n\nFor example,\nExample 1 - How many entries of records are present?, 
+the SQL command will be something like this SELECT COUNT(*) FROM STUDENT ;
+\nExample 2 - Tell me all the students studying in Data Science class?, 
+the SQL command will be something like this SELECT * FROM STUDENT 
+where CLASS="Data Science"; And show me the data in tabular format if possible.
+also the sql code should not have ``` in beginning or end and sql word in output
+"""
+
+# Streamlit UI
+input_text = st.text_area("Input: ", key="input")
+submit_button = st.button("Ask the question")
+
+if submit_button and input_text:
+    # Get response from Gemini model
+    response = get_gemini_response(input_text)
+    
+    # Add user query and response to session state chat history
+    st.session_state['chat_history'].append(("You", input_text))
+    st.subheader("The Response is")
+    for chunk in response:
+        st.write(chunk.text)
+        st.session_state['chat_history'].append(("Bot", chunk.text))
+
+# Display chat history
+st.subheader("The Chat History is")
+for role, text in st.session_state['chat_history']:
+    st.write(f"{role}: {text}")
+
+# Function to get text from PDF
 def get_pdf_text(pdf_docs):
     text = ""
     for pdf in pdf_docs:
@@ -37,23 +90,15 @@ def get_text_chunks(text):
     chunks = text_splitter.split_text(text)
     return chunks
 
-# Function to create a vector store
+# Function to create vector store
 def get_vector_store(text_chunks):
     embeddings = GoogleGenerativeAIEmbeddings(model="models/embedding-001")
     vector_store = FAISS.from_texts(text_chunks, embedding=embeddings)
     vector_store.save_local("faiss_index")
 
-# Function to retrieve query from the database
-def read_sql_query(sql, db):
-    conn = sqlite3.connect(db)
-    cur = conn.cursor()
-    cur.execute(sql)
-    rows = cur.fetchall()
-    conn.close()
-    return rows
-
-# Function to get conversational chain
+# Function to initialize conversational chain
 def get_conversational_chain():
+    model = ChatGoogleGenerativeAI(model="gemini-pro", temperature=0.3)
     prompt_template = """
     Answer the question as detailed as possible from the provided context, make sure to provide all the details, if the answer is not in
     provided context just say, "answer is not available in the context", don't provide the wrong answer\n\n
@@ -62,53 +107,35 @@ def get_conversational_chain():
 
     Answer:
     """
-    model = ChatGoogleGenerativeAI(model="gemini-pro", temperature=0.3)
     prompt = PromptTemplate(template=prompt_template, input_variables=["context", "question"])
     chain = load_qa_chain(model, chain_type="stuff", prompt=prompt)
     return chain
 
-# Streamlit App
-st.set_page_config(page_title="Consolidated Application")
-
-st.header("Consolidated Application")
-
-# Dropdown menu for selecting functionality
-selected_option = st.sidebar.selectbox("Select an option", ["Gemini LLM", "Chat with PDF", "Image Description Generation"])
-
-if selected_option == "Gemini LLM":
-    st.subheader("Gemini LLM Application")
-
-    gemini_input = st.text_input("Input for Gemini LLM", key="gemini_input")
-
-    uploaded_image = st.file_uploader("Choose an image...", type=["jpg", "jpeg", "png"])
-
-    if st.button("Generate Response for Gemini LLM"):
-        gemini_response = get_gemini_response(gemini_input, image=uploaded_image)
-        st.subheader("Gemini LLM Response")
-        st.write(gemini_response)
-
-elif selected_option == "Chat with PDF":
-    st.subheader("Chat with PDF using Gemini")
-
-    pdf_question = st.text_input("Ask a Question from the PDF Files", key="pdf_question")
-    uploaded_pdf = st.file_uploader("Upload your PDF Files", type="pdf", accept_multiple_files=True)
-
-    if st.button("Submit & Process PDF"):
-        raw_text = get_pdf_text(uploaded_pdf)
-        text_chunks = get_text_chunks(raw_text)
-        get_vector_store(text_chunks)
-        st.success("PDF Processing Complete")
-
-elif selected_option == "Image Description Generation":
-    st.subheader("Image Description Generation")
-
-    image_input = st.text_input("Input for Image Description Generation", key="image_input")
-    uploaded_image = st.file_uploader("Choose an image...", type=["jpg", "jpeg", "png"])
-
-    if st.button("Generate Image Description"):
-        image_response = get_gemini_response(image_input, image=uploaded_image)
-        st.subheader("Image Description")
-        st.write(image_response)
-
-
-        
+# Function to process user input for PDF interaction
+def user_input(user_question):
+    embeddings = GoogleGenerativeAIEmbeddings(model="models/embedding-001")
+    new_db = FAISS.load_local("faiss_index", embeddings, allow_dangerous_deserialization=True)
+    docs = new_db.similarity_search(user_question)
+    chain = get_conversational_chain()
+    response = chain({"input_documents": docs, "question": user_question}, return_only_outputs=True)
+    st.write("Reply: ", response["output_text"])
+
+# Main function
+def main():
+    st.set_page_config("Chat PDF")
+    st.header("Chat with PDF using Gemini💁")
+    user_question = st.text_input("Ask a Question from the PDF Files")
+    if user_question:
+        user_input(user_question)
+    with st.sidebar:
+        st.title("Menu:")
+        pdf_docs = st.file_uploader("Upload your PDF Files and Click on the Submit & Process Button", accept_multiple_files=True)
+        if st.button("Submit & Process"):
+            with st.spinner("Processing..."):
+                raw_text = get_pdf_text(pdf_docs)
+                text_chunks = get_text_chunks(raw_text)
+                get_vector_store(text_chunks)
+                st.success("Done")
+
+if __name__ == "__main__":
+    main()